Statistics Flashcards
What are the four different scales of measurement?
- NOIR
- Nominal
- Ordinal
- Interval
- Ratio
Describe the Nominal Scale of Measurement
- Numerals represent category labels only
- Sex, Nationality, Blood Type, etc
Describe the Ordinal Scale of Measurement
- Numbers indicate rank order
- Intervals may not be equally spaced
- Manual Muscle Test, NPRS, Etc
Describe the Interval Scale of Measurement
- Equal Intervals Between Numbers
- Not related to true zero, not representing absolute quantity
- Calendar Years, IQ level
Describe the Ratio Scale of Measurement
- Numbers represent units with equal intervals
- Measured from True Zero
- Distance, Age, Weight, etc
What is Predictive Validity?
- Attempts to establish that a test with be a valid predictor of some future criterion score
- SAT test used to determine future academic success at college
What is Construct Validity?
- The ability of a test an instrument to measure an abstract concept or construct
- Never fully realize due to the difficulty to define constructs (because constructs are not “real”)
What is a Positive Predictive Value?
- The likelihood that a person who tests positive actually has the disease
- Number of patients with the disease divided by Number of positive tests
What is a Negative Predictive Value?
- Probability that a person who tests negative does not have the disease
- Number of patients without disease divided by Number of Negative Tests
What is Prevalence?
- Number of cases of a condition existing in a given population at any one time
What is Incidence?
- Number of new cases of a condition over a certain period of time
What is effect size?
- Standardized measure of change ranging from 0-1
- Below .4 small
- .5 Moderate
- .8 Large
What is a research Hypothesis?
- The researchers true expectation of the results
What is the Statistical/ Null Hypothesis?
- Expectation that there will be no difference between independent and dependent variables
What is the difference between a Single Blind and Double Blind Study?
- Single Blind, only investigator or subject is blinded
- Double Blind, Investigators and subjects are blinded
What is Type 1 Error?
- The Risk of saying a difference exists when one does not
- Backing a Loser
- Expressed by Alpha value, Typically at .05
What is Type 2 Error?
- Risk of stating there is no difference when one does exist
- Rejecting a Winner
- Expressed by Beta, Typically between .05 and .20
What are the Determinants of Statistical Power?
- SAVE
- Sample Size
- Alpha Value
- Variance
- Effect Size
What is Face Validity?
- Instrument appears to test what it is supposed to test
What is Content Validity?
- Items that make up an instrument adequately test the universe of content that defines the variable being measured
- Used Most often in questionnaires
What is Concurrent Validity?
- Establishes validity when two measures are taken at relatively the same time
- Used when target is considered more efficient than the gold standard